© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107845
    Prev
    Next
    INDEX
    Explanations

    business entities and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beijo
    -0.93
     سایر
    -0.91
    lts
    -0.91
     espelho
    -0.89
     verdaderas
    -0.87
    {?>
    -0.85
    >
    -0.84
    genas
    -0.82
    +");
    -0.82
     parishes
    -0.81
    POSITIVE LOGITS
     retailer
    1.49
     nonprofit
    1.37
     multinational
    1.34
     Swedish
    1.34
    Swedish
    1.33
     giant
    1.28
     popular
    1.28
     insurer
    1.27
     Italian
    1.22
    总部
    1.20
    Activations Density 0.179%

    No Known Activations